News Minimalist [1] is one way, where it aggregates stories across outlets and uses LLMs to remove clickbait from titles. It also assigns loose 'scores' to each story to approximate how 'important' it is, which I've found to be directionally useful.

Ultimately, it comes down to why one consumes news at all. If it's to have something to discuss around the water cooler or dinner table, that's a very different use case than someone trying to pattern match on world events for trading stocks or selling their wares.

[1] https://www.newsminimalist.com/

I’m working on this as a personal project so I’m interested in other’s solutions!

I’m not working on it toooo hard. This is something I think some AI software tool might swoop in and solve before I can build something I’m happy with.